David Oks

I do stuff @OpenAI, I occasionally write essays at

[David Oks @davideoks]

@albrgr he also extended it to say that diffusion of iron (unlike tin, ubiquitous and hard to monopolize) caused the collapse of the great bronze age empires … very controversial argument

[David Oks @davideoks]

@albrgr this is a very old idea fwiw! V. Gordon Childe made this argument in the 1930s

[David Oks @davideoks]

@St2station Norman Stone such a gifted writer, disappointing as his output ultimately was. Highly recommend his quite legendary LRB obituary of E. H. Carr … so brutal

[David Oks @davideoks]

@bucephalus424 Congratulations! I hope you teach the Sanchez-Sibony book for the first course (and maybe Stefan Link too?)

[Jakub Pachocki @merettm]

I want to prevent a race into unmonitorability kicked off by confused reporting. The depth of the computation graph for our present frontier models, including Astra, is within a factor of two of GPT-4.

OpenAI has worked to preserve and utilize chain-of-thought monitoring since our very first reasoning models. We deeply care about this technique, as it can give us a view into how model alignment generalizes from its training distribution. I do think it is fragile and unfortunately trending in a negative direction, for reasons not contingent on architecture changes that I will write about soon. But there are things we can do to strengthen it, and it's a core goal of our current research program.

[David Oks @davideoks]

@polanskydj this + Stammering Century (also NYRB Classic, also American history) are fantastic

[David Oks @davideoks]

@HunterWieman @BasilHalperin yeah I don't expect any government to do it, but seems to be the consistent thing to do if you're in that position and have those beliefs

[David Oks @davideoks]

@HunterWieman @BasilHalperin current yield on 30-year Nigeria sovereign debt is south of 15 percent it seems from cursory search ... if you're an AGI-pilled finance minister you could perhaps take out debt and buy basket of AGI-ish equities (the memory makers, the labs, Nvidia, so on)

[David Oks @davideoks]

@Tim_Hua_ labor share of income (as FRED measures it at least) is a very lossy reflection of what people think it measures, affected by a ton of tax stuff. a lot of the decline in labor share over the last few decades is reclassification of labor income as capital income through S corps

[David Oks @davideoks]

@anton_d_leicht @AmericanAffrs great choice of author @daniel_bring!

[David Oks @davideoks]

@ohlennart Congratulations Lennart!

[David Oks @davideoks]

@ahall_research @AnthropicAI Congratulations Andy!

[Micah Carroll @MicahCarroll]

We are hiring!

This may be the best time ever to join: we are incredibly bandwidth bottlenecked and there is a lot of support for almost any impactful misalignment work you can think of. I think we also have a pretty good epistemic environment and a very fun team

Topics: all-things monitoring, misalignment & monitorability assessments, misalignment science, helping set up 3P auditing (e.g. recent Redwood collab), communicating risk externally (system cards/blogs, safety cases, etc)

RSI/misalignment subteam: https://t.co/YHLMCYwWOe

[David Oks @davideoks]

@alexolegimas @Chris_arnade Ravelstein is great! Strongly recommend it. Henderson the Rain King too. Herzog is very florid, overflowing, a bit much.

[will depue @willdepue]

charles yang david oks henry williams. the gang invades anthropic & openai frontier policy

[Joe Weisenthal @TheStalwart]

Good hires by OpenAI. @davideoks and @humford were both on Odd Lots in 2023, talking about how so many countries around the world have run into a development well https://t.co/yuE7hwvgnl

[Dean W. Ball @deanwball]

Very pleased to welcome @davideoks and @humford to the Strategic Futures team. These are two tremendous talents, and I believe they will cast the unfolding AI revolution in new and beautiful light.

[Charles Yang @charlesxjyang]

In some life news: I started at the Anthropic Institute as chief of staff last month!
I'm excited to be working with @jackclarksf and the institute's research teams — from economics and rule of law, to societal impacts and the frontier red team — to surface important data from inside Anthropic about what's happening at the frontier of AI.

[Henry Williams @humford]

An announcement: I've joined @deanwball's Strategic Futures team at OpenAI to help shape frontier AI policy. Our work will focus on on how transformative AI will reshape the economy, our institutions, and free society, and how human agency can be preserved in the process.

[David Oks @davideoks]

A personal update: I’ve joined @OpenAI’s Strategic Futures team, working under @deanwball, to help prepare the world for transformative AI. Excited to get to work.